Generation-Based Target Speech Extraction with Speech Discretization and Vocoder.
Linfeng YuWangyou ZhangChenpeng DuLeying ZhangZheng LiangYanmin QianPublished in: ICASSP (2024)
Keyphrases
- speech recognition
- speech synthesis
- text to speech
- database
- speech signal
- recognition engine
- audio visual
- automatic speech recognition
- noisy environments
- hidden markov models
- spoken language
- speaker recognition
- hearing impaired
- audio stream
- vocal tract
- multi stream
- multimodal interfaces
- generation process
- image sequences
- machine learning
- neural network
- data sets